R Notebook

# Load packages
library(ggplot2)
library(dplyr)
library(tidyr)
library(tidyverse)
library(plotly)

# Read datasets/confirmed_cases_worldwide.csv into confirmed_cases_worldwide
coronavirus <- read_csv("./data/coronavirus.csv")

Parsed with column specification:
cols(
  date = col_date(format = ""),
  province = col_logical(),
  country = col_character(),
  lat = col_double(),
  long = col_double(),
  type = col_character(),
  cases = col_double()
)
45800 parsing failures.
  row      col           expected  actual                     file
37001 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37002 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37003 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37004 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37005 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
..... ........ .................. ....... ........................
See problems(...) for more details.

head(coronavirus)

str(coronavirus)

tibble [157,000 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ date    : Date[1:157000], format: "2020-01-22" "2020-01-23" "2020-01-24" ...
 $ province: logi [1:157000] NA NA NA NA NA NA ...
 $ country : chr [1:157000] "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
 $ lat     : num [1:157000] 33.9 33.9 33.9 33.9 33.9 ...
 $ long    : num [1:157000] 67.7 67.7 67.7 67.7 67.7 ...
 $ type    : chr [1:157000] "confirmed" "confirmed" "confirmed" "confirmed" ...
 $ cases   : num [1:157000] 0 0 0 0 0 0 0 0 0 0 ...
 - attr(*, "problems")= tibble [45,800 × 5] (S3: tbl_df/tbl/data.frame)
  ..$ row     : int [1:45800] 37001 37002 37003 37004 37005 37006 37007 37008 37009 37010 ...
  ..$ col     : chr [1:45800] "province" "province" "province" "province" ...
  ..$ expected: chr [1:45800] "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" ...
  ..$ actual  : chr [1:45800] "Alberta" "Alberta" "Alberta" "Alberta" ...
  ..$ file    : chr [1:45800] "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" ...
 - attr(*, "spec")=
  .. cols(
  ..   date = col_date(format = ""),
  ..   province = col_logical(),
  ..   country = col_character(),
  ..   lat = col_double(),
  ..   long = col_double(),
  ..   type = col_character(),
  ..   cases = col_double()
  .. )

# # See the result
bycountry <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` ungrouping output (override with `.groups` argument)

bycountry

confirmed_cases = coronavirus %>% 
  group_by(date) %>%
  filter(type == "confirmed") %>%
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

# confirmed_cases_china = coronavirus %>%
#   group_by(date) %>%
#   filter(country == "China", type == "confirmed")%>% 
#   summarize(cases = sum(cases)) %>%
#   mutate(cumsum = cumsum(cases))
# confirmed_cases_china



(confirmed_cases)

NA
NA
NA
NA
NA

coronavirus %>% 
  filter(date == max(date)) %>%
  select(country, type, cases) %>%
  group_by(country, type) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type,
              values_from = total_cases) %>%
  arrange(-confirmed)

`summarise()` regrouping output by 'country' (override with `.groups` argument)

coronavirus %>% 
  group_by(type, date) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type, values_from = total_cases) %>%
  arrange(date) %>%
  mutate(active = confirmed - death - recovered) %>%
  mutate(active_total = cumsum(active),
                recovered_total = cumsum(recovered),
                death_total = cumsum(death)) %>%
  plot_ly(x = ~ date,
                  y = ~ active_total,
                  name = 'Active', 
                  fillcolor = '#1f77b4',
                  type = 'scatter',
                  mode = 'none', 
                  stackgroup = 'one') %>%
  add_trace(y = ~ death_total, 
             name = "Death",
             fillcolor = '#E41317') %>%
  add_trace(y = ~recovered_total, 
            name = 'Recovered', 
            fillcolor = 'forestgreen') %>%
  layout(title = "Distribution of Covid19 Cases Worldwide",
         legend = list(x = 0.1, y = 0.9),
         yaxis = list(title = "Number of Cases"),
         xaxis = list(title = "Source: Johns Hopkins University Center for Systems Science and Engineering"))

`summarise()` regrouping output by 'type' (override with `.groups` argument)
`arrange_()` is deprecated as of dplyr 0.7.0.
Please use `arrange()` instead.
See vignette('programming') for more help
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.

conf_df <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases) %>%
  mutate(parents = "Confirmed") %>%
  ungroup() 

`summarise()` ungrouping output (override with `.groups` argument)

  
  plot_ly(data = conf_df,
          type= "treemap",
          values = ~total_cases,
          labels= ~ country,
          parents=  ~parents,
          domain = list(column=0),
          name = "Confirmed",
          textinfo="label+value+percent parent")

ggplot(confirmed_cases, aes(x = date, y = cum_cases)) +
  geom_line(aes(x = date, y = cum_cases)) +
  ylab("Cumulative confirmed cases")

Error in FUN(X[[i]], ...) : object 'cum_cases' not found

head(coronavirus)

coronavirus = tibble::rowid_to_column(coronavirus, "ID")
head(coronavirus)

# coronavirus = coronavirus %>%
#   group_by(ID) %>% 
#   mutate(cum_cases = cumsum(cases))
# coronavirus %>% head(70)

mutate(group_by(coronavirus, ID), cumsum = cumsum(cases))

# df <- data.frame(id = rep(1:3, each = 5),
#                  hour = rep(1:5, 3),
#                  value = sample(1:15))
# 
# mutate(group_by(df,id), cumsum=cumsum(value))

confirmed_cases_china = coronavirus %>%
  group_by(date) %>%
  filter(country == "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

confirmed_cases_china

confirmed_cases_china %>% 
  group_by(date) %>% 
  summarize(cases = sum(cases)) %>% 
  select(date, country, cases, cumsum)

`summarise()` ungrouping output (override with `.groups` argument)
Error: Can't subset columns that don't exist.
x Column `country` doesn't exist.

plt_cum_confirmed_cases_china <- ggplot(confirmed_cases_china, aes(date, cumsum)) +
  geom_line() +
  ylab("Cumulative confirmed cases") 

# See the plot
plt_cum_confirmed_cases_china

who_events <- tribble(
  ~ date, ~ event,
  "2020-01-30", "Global health emergency declared",
  "2020-03-11", "Pandemic declared",
  "2020-02-13", "China reporting change"
) %>%
  mutate(date = as.Date(date))

# Using who_events, add vertical dashed lines with an xintercept at date
# and text at date, labeled by event, and at 100000 on the y-axis
plt_cum_confirmed_cases_china + 
  geom_vline(aes(xintercept = date), data = who_events, linetype = "dashed") +
  geom_text(aes(x = date, label = event), data = who_events, y = 1e5)

# Filter for China, from Feb 15
china_after_feb15 <- confirmed_cases_china %>%
  filter(date >= "2020-02-15")

# Using china_after_feb15, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
ggplot(china_after_feb15, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

not_china = coronavirus %>%
  group_by(date) %>%
  filter(country != "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

not_china

# not_china %>% 
#   group_by(date) %>% 
#   summarize(cases = sum(cases)) %>% 
#   select(date, country, cases, cumsum)


glimpse(not_china)

Rows: 200
Columns: 3
$ date   <date> 2020-01-22, 2020-01-23, 2020-01-24, 2020-01-25, 2020-01-26, 2020-01-27, 2…
$ cases  <dbl> 7, 4, 10, 7, 15, 7, 19, 10, 14, 32, 22, 10, 14, 20, 12, 12, 70, 30, 15, 84…
$ cumsum <dbl> 7, 11, 21, 28, 43, 50, 69, 79, 93, 125, 147, 157, 171, 191, 203, 215, 285,…

not_china2 = coronavirus %>%
  group_by(date) %>%
  filter(country != "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

not_china2

world_after_feb15 <- all_countries %>%
  filter(date >= "2020-02-15")

Error in eval(lhs, parent, parent) : object 'all_countries' not found

# Using not_china, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
plt_not_china_trend_lin <- ggplot(not_china, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

# See the result
plt_not_china_trend_lin 

plt_not_china_trend_lin + 
  scale_y_log10()

Filter by top 7 countries

target = c("Brazil", "India", "Mexico", "Peru", "Russia", "South Africa", "US")
top_7countries = bycountry %>% 
  filter(country %in% target)

top_7countries

NA

ggplot(top_7countries, aes(date, total_cases))  +
    geom_line(aes(group = country, color = country))+
    ylab("Cumulative confirmed cases")